cells2table 0.2.3

Table image parsing with cell detection models

cells2table

Parsing tables in document images with cell detection models

Implemented pipelines

PaddlePaddle

• Classification model (wired / wireless)
• Cell detection model with different weights for each class

Uses ONNX weights downloaded automatically from Hugging Face on first use.

Instalation

With uv, add to your project with:

uv add cells2table

ONNX models need a ONNX Runtime installed to run. You can install one on your own or use one of the optionals already configured.

Optional	Description
docling	For docling usage
huggingface	For downloading models
onnx_cuda	For NVIDIA GPUs
onnx_openvino	For Intel GPUs and CPUs
onnx_cpu	Default CPU runtime

Usage

cells2table only extract structural information from the tables. Another library is needed to extract content from the cells.

Docling

A docling plugin is provided to allow integrating cells2table in a complete pipeline.

Usage example:

from cells2table.docling import CustomDoclingTableStructureOptions

pipeline_options = PdfPipelineOptions(
    allow_external_plugins=True,
    table_structure_options=CustomDoclingTableStructureOptions(),
)

converter = DocumentConverter(
    format_options={
        InputFormat.PDF: PdfFormatOption(pipeline_options=pipeline_options),
        InputFormat.IMAGE: PdfFormatOption(pipeline_options=pipeline_options),
    }
)

result = converter.convert("path/to/document.pdf")
print(result.document.export_to_markdown())